© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7425
    Prev
    Next
    INDEX
    Explanations

    first-person subjective expressions

    oai_token-act-pair · gemini-2.0-flash

    Expressing feelings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poveznice
    -0.59
     Reck
    -0.53
    CTOR
    -0.52
     Temper
    -0.50
    TypedDataSet
    -0.50
     Concern
    -0.50
     hl
    -0.49
     CanadaChoose
    -0.48
    ỡng
    -0.48
     Same
    -0.47
    POSITIVE LOGITS
     '\\;'
    0.78
    CppMethod
    0.77
    UIControlState
    0.69
    ArgsConstructor
    0.66
    ("")]
    0.63
     تضيفلها
    0.60
     للاسماء
    0.59
    AxisAlignment
    0.56
     viewDidLoad
    0.54
    Superview
    0.51
    Activations Density 0.510%

    No Known Activations